Out of distribution (OOD) medical images are frequently encountered, e.g. because of site- or scanner differences, or image corruption. OOD images come with a risk of incorrect image segmentation, potentially negatively affecting downstream diagnoses or treatment. To ensure robustness to such incorrect segmentations, we propose Laplacian Segmentation Networks (LSN) that jointly model epistemic (model) and aleatoric (data) uncertainty in image segmentation. We capture data uncertainty with a spatially correlated logit distribution. For model uncertainty, we propose the first Laplace approximation of the weight posterior that scales to large neural networks with skip connections that have high-dimensional outputs. Empirically, we demonstrate that modelling spatial pixel correlation allows the Laplacian Segmentation Network to successfully assign high epistemic uncertainty to out-of-distribution objects appearing within images.

翻译：分布外（OOD）医学图像经常出现，例如由于站点或扫描仪差异，或图像损坏所致。OOD图像存在分割错误的风险，可能对下游诊断或治疗产生负面影响。为了增强对此类错误分割的鲁棒性，我们提出了拉普拉斯分割网络（LSN），该网络联合建模图像分割中的认知（模型）不确定性和偶然（数据）不确定性。我们通过空间相关的logit分布捕捉数据不确定性。针对模型不确定性，我们首次提出了一种权重后验的拉普拉斯近似方法，该方法可扩展到带有跳跃连接且具有高维输出的大规模神经网络。实验表明，通过对空间像素相关性进行建模，拉普拉斯分割网络能够成功地将高认知不确定性赋予图像中出现的分布外目标。